Open nawang0226 opened 5 years ago
Hi, I met the same error, did you handle it?
no, haven't handle it.
I am sorry, last week I made a update for supporting varied numbers of ROIs for forward operations in case of not enough GPU memory. And you can fix the bugs as following: in network.py file, in _add_losses functions, in lines 244, change to self.get_refine_supervision(det_cls_product, self._image_gt_summaries['ss_boxes'][self.ss_boxes_indexes ,:],self._image_gt_summaries['image_level_label']). And for line 257 do the same operation. And I will fix this small bugs soon.
Hi, following the ReadMe, whatever it just doesn't work and I don't know how to fix it. The problem is
/data3/CV_WN/MELM-master/output/vgg16/voc_2007_trainval/default
TensorFlow summaries will be saved to/data3/CV_WN/MELM-master/tensorboard/vgg16/voc_2007_trainval/default
Loaded datasetvoc_2007_test
for training Set proposal method: selective_search Preparing training data... voc_2007_test ss roidb loaded from /data3/CV_WN/MELM-master/data/cache/voc_2007_test_selective_search_roidb.pkl done 4952 validation roidb entries Filtered 0 roidb entries: 10022 -> 10022 Filtered 0 roidb entries: 4952 -> 4952 Solving... Loading initial model weights from data/imagenet_weights/vgg16.pth Loaded. Traceback (most recent call last): File "./tools/trainval_net.py", line 130, inThanks for all have you done and look forward to your early reply to this problem.